{"id":"https://openalex.org/W7147239264","doi":"https://doi.org/10.1093/jamia/ocag037","title":"A critical evaluation of generative query expansion on biomedical literature retrieval","display_name":"A critical evaluation of generative query expansion on biomedical literature retrieval","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7147239264","doi":"https://doi.org/10.1093/jamia/ocag037","pmid":"https://pubmed.ncbi.nlm.nih.gov/41921511"},"language":"en","primary_location":{"id":"doi:10.1093/jamia/ocag037","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocag037","pdf_url":null,"source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1093/jamia/ocag037","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061866993","display_name":"Yilu Fang","orcid":"https://orcid.org/0000-0002-2681-1931"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yilu Fang","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University , New York, NY,"],"raw_orcid":"https://orcid.org/0000-0002-2681-1931","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University , New York, NY,","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132702160","display_name":"Gongbo Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gongbo Zhang","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University , New York, NY,"],"raw_orcid":"https://orcid.org/0009-0001-0077-3615","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University , New York, NY,","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132568331","display_name":"Fangyi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fangyi Chen","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University , New York, NY,"],"raw_orcid":"https://orcid.org/0000-0003-2926-1063","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University , New York, NY,","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yifan Peng","orcid":"https://orcid.org/0000-0001-9309-8331"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I4387153466","display_name":"Weill Cornell Medicine","ror":"https://ror.org/02r109517","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Peng","raw_affiliation_strings":["Department of Population Health Sciences, Weill Cornell Medicine , New York, NY,"],"raw_orcid":"https://orcid.org/0000-0001-9309-8331","affiliations":[{"raw_affiliation_string":"Department of Population Health Sciences, Weill Cornell Medicine , New York, NY,","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123344858","display_name":"Chunhua Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunhua Weng","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University , New York, NY,"],"raw_orcid":"https://orcid.org/0000-0002-9624-0214","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University , New York, NY,","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5061866993"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":{"value":3967,"currency":"USD","value_usd":3967},"apc_paid":{"value":3967,"currency":"USD","value_usd":3967},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.53103434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"6","first_page":"1121","last_page":"1133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7512000203132629,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7512000203132629,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.16899999976158142,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10206","display_name":"Meta-analysis and systematic reviews","score":0.00989999994635582,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.8431000113487244},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7785000205039978},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.748199999332428},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5080999732017517},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5054000020027161},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.48539999127388},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.4560999870300293}],"concepts":[{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.8431000113487244},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7785000205039978},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.748199999332428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7325000166893005},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5453000068664551},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5080999732017517},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5054000020027161},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.48539999127388},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.4560999870300293},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4311999976634979},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4156999886035919},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.39640000462532043},{"id":"https://openalex.org/C96956885","wikidata":"https://www.wikidata.org/wiki/Q6138701","display_name":"RDF query language","level":5,"score":0.36730000376701355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32910001277923584},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.2766999900341034},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.25209999084472656}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/jamia/ocag037","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocag037","pdf_url":null,"source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},{"id":"pmid:41921511","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41921511","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association : JAMIA","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:13197180","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13197180/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Am Med Inform Assoc","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/jamia/ocag037","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocag037","pdf_url":null,"source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.683515727519989}],"awards":[{"id":"https://openalex.org/G1172121642","display_name":null,"funder_award_id":"UL1TR001873","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2214230469","display_name":null,"funder_award_id":"UL1TR002384","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3713498508","display_name":null,"funder_award_id":"R01LM014344, R01LM014573, and T15LM007079","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G4713501941","display_name":null,"funder_award_id":"R01LM014344","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G7888995200","display_name":null,"funder_award_id":"R01LM014573","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G8763244384","display_name":null,"funder_award_id":"T15LM007079","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"},{"id":"https://openalex.org/F4320337472","display_name":"National Center for Advancing Translational Sciences","ror":"https://ror.org/04pw6fb54"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1845198550","https://openalex.org/W1981208470","https://openalex.org/W1993692165","https://openalex.org/W2034199740","https://openalex.org/W2037210357","https://openalex.org/W2039612385","https://openalex.org/W2057761625","https://openalex.org/W2136029572","https://openalex.org/W2142325887","https://openalex.org/W2159583324","https://openalex.org/W2486678281","https://openalex.org/W2741307002","https://openalex.org/W2889792925","https://openalex.org/W2951534261","https://openalex.org/W3095490894","https://openalex.org/W3180230246","https://openalex.org/W3215906209","https://openalex.org/W4252076394","https://openalex.org/W4361001766","https://openalex.org/W4364386924","https://openalex.org/W4367189613","https://openalex.org/W4375870261","https://openalex.org/W4385565351","https://openalex.org/W4387213419","https://openalex.org/W4388409299","https://openalex.org/W4389520758","https://openalex.org/W4391544808","https://openalex.org/W4401042882","https://openalex.org/W4401306886","https://openalex.org/W4402387323","https://openalex.org/W4402669713","https://openalex.org/W4402670290","https://openalex.org/W4404330874","https://openalex.org/W4404782251","https://openalex.org/W4411638747","https://openalex.org/W4413051957"],"related_works":[],"abstract_inverted_index":{"OBJECTIVE:":[0],"To":[1],"evaluate":[2],"the":[3,192,220,226,235],"effectiveness":[4],"of":[5,58,86,108,118,122,127,145,166,186,197,229],"generative":[6,20],"query":[7,21,72,114,160,187,208],"expansion":[8,22,73,115,188,193,209],"for":[9,32,132],"biomedical":[10,33,230],"literature":[11,34,231],"retrieval.":[12,35],"MATERIALS":[13],"AND":[14,182],"METHODS:":[15],"We":[16,36,52],"thoroughly":[17],"examined":[18],"eight":[19],"methods":[23,194],"using":[24],"three":[25],"large":[26],"language":[27],"models":[28,175],"across":[29],"five":[30],"datasets":[31],"further":[37],"performed":[38],"a":[39,55,84,125,216],"quantitative":[40],"analysis,":[41,47],"including":[42],"performance":[43,178],"comparisons,":[44],"rank":[45],"transition":[46],"and":[48,78,88,98,110,120,129,137,147,152,157,168,172,195,233],"article-type":[49],"effect":[50],"analysis.":[51],"also":[53],"conducted":[54],"qualitative":[56],"examination":[57],"representative":[59],"cases,":[60],"from":[61,94,100],"which":[62],"we":[63],"derived":[64],"an":[65],"error":[66],"taxonomy.":[67],"RESULTS:":[68],"On":[69],"BioASQ-Y/N,":[70],"GPT-4o-based":[71],"shifts":[74],"Recall@10":[75],"to":[76,80,83,96,102,142,179,203,237],"0.417-0.512":[77],"nDCG@10":[79,99],"0.358-0.479,":[81],"relative":[82,141],"baseline":[85,106,126,143,164],"0.491":[87],"0.456.":[89],"For":[90,112,149],"PubMedQA,":[91],"Precision@1":[92],"ranges":[93],"0.764":[95],"0.876":[97],"0.847":[101],"0.931,":[103],"compared":[104,162],"with":[105,163],"values":[107],"0.893":[109],"0.935.":[111],"2019-Trec-PM,":[113],"yields":[116],"Recall@100":[117,134,151],"0.217-0.256":[119],"nDCG@100":[121,138,153],"0.272-0.312,":[123],"versus":[124],"0.227":[128],"0.274.":[130],"Similarly,":[131],"2018-TREC-PM,":[133],"spans":[135,139],"0.169-0.227":[136],"0.195-0.250,":[140],"scores":[144],"0.164":[146],"0.191.":[148],"2017-TREC-PM,":[150],"fall":[154],"within":[155],"0.111-0.139":[156],"0.154-0.191":[158],"under":[159],"expansion,":[161],"metrics":[165],"0.102":[167],"0.147.":[169],"Both":[170],"general-purpose":[171],"domain-specific":[173,239],"Llama-based":[174],"demonstrate":[176],"similar":[177],"GPT-4o.":[180],"DISCUSSION":[181],"CONCLUSION:":[183],"The":[184],"impact":[185,218],"varies":[189],"significantly":[190],"by":[191],"type":[196],"evidence,":[198],"but":[199,214],"is":[200],"relatively":[201],"agnostic":[202],"backbone":[204],"model":[205],"choice.":[206],"Notably,":[207],"primarily":[210],"affects":[211],"article":[212],"ranking":[213],"has":[215],"limited":[217],"on":[219],"screening":[221],"stage.":[222],"Our":[223],"findings":[224],"underscore":[225],"unique":[227],"challenges":[228],"retrieval":[232,241],"highlight":[234],"need":[236],"develop":[238],"information":[240],"techniques.":[242]},"counts_by_year":[],"updated_date":"2026-05-26T13:28:51.108037","created_date":"2026-04-02T00:00:00"}